{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automated-analysis-and-prediction-of-job","title":"Automated Analysis and Prediction of Job Interview Performance","arxiv_id":"1504.03425","date":"2015-04-14","proceeding":null,"authors":["Iftekhar Naim","M. Iftekhar Tanveer","Daniel Gildea","Mohammed","Hoque"],"abstract":"We present a computational framework for automatically quantifying verbal and\nnonverbal behaviors in the context of job interviews. The proposed framework is\ntrained by analyzing the videos of 138 interview sessions with 69\ninternship-seeking undergraduates at the Massachusetts Institute of Technology\n(MIT). Our automated analysis includes facial expressions (e.g., smiles, head\ngestures, facial tracking points), language (e.g., word counts, topic\nmodeling), and prosodic information (e.g., pitch, intonation, and pauses) of\nthe interviewees. The ground truth labels are derived by taking a weighted\naverage over the ratings of 9 independent judges. Our framework can\nautomatically predict the ratings for interview traits such as excitement,\nfriendliness, and engagement with correlation coefficients of 0.75 or higher,\nand can quantify the relative importance of prosody, language, and facial\nexpressions. By analyzing the relative feature weights learned by the\nregression models, our framework recommends to speak more fluently, use less\nfiller words, speak as \"we\" (vs. \"I\"), use more unique words, and smile more.\nWe also find that the students who were rated highly while answering the first\ninterview question were also rated highly overall (i.e., first impression\nmatters). Finally, our MIT Interview dataset will be made available to other\nresearchers to further validate and expand our findings.","url_abs":"http://arxiv.org/abs/1504.03425v1","url_pdf":"http://arxiv.org/pdf/1504.03425v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automated-analysis-and-prediction-of-job","repo_url":"https://github.com/scoville/sentiment-audio-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1504.03425","atlas_url":"https://app.syntology.ai/?focus=1504.03425","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}